[X86] Fold MMX_MOVD64from64rr + store to MMX_MOVQ64mr instead of MMX_MOVD64from64mr.

[craig.topper]

Summary

MMX_MOVD64from64rr moves an MMX register to a 64-bit GPR.

MMX_MOVD64from64mr is the memory version of moving a MMX register to a
64-bit GPR. It requires the REX.W bit to be set. There are no isel
patterns that use this instruction.

MMX_MOVQ64mr is the MMX register store instruction. It doesn't
require a REX.W prefix. This makes it one byte shorter to encode
than MMX_MOVD64from64mr in many cases.

Both store instructions output the same mnemonic string. The assembler
would choose MMX_MOVQ64mr if it was to parse the output. Which is
another reason using it is the correct thing to do.

[RKSimon]

nice catch! LGTM

[skan]

LGTM

llvm/lib/Target/X86/X86InstrFoldTables.cpp

 //===-- X86InstrFoldTables.cpp - X86 Instruction Folding Tables -----------===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
static const X86MemoryFoldTableEntry MemoryFoldTable2Addr[] = {
   { X86::XOR64ri8,    X86::XOR64mi8,   0 },
   { X86::XOR64rr,     X86::XOR64mr,    0 },
   { X86::XOR8ri,      X86::XOR8mi,     0 },
   { X86::XOR8ri8,     X86::XOR8mi8,    0 },
   { X86::XOR8rr,      X86::XOR8mr,     0 },
 };
 
 static const X86MemoryFoldTableEntry MemoryFoldTable0[] = {
   { X86::BT16ri8,             X86::BT16mi8,             TB_FOLDED_LOAD },
   { X86::BT32ri8,             X86::BT32mi8,             TB_FOLDED_LOAD },
   { X86::BT64ri8,             X86::BT64mi8,             TB_FOLDED_LOAD },
   { X86::CALL16r,             X86::CALL16m,             TB_FOLDED_LOAD },
   { X86::CALL16r_NT,          X86::CALL16m_NT,          TB_FOLDED_LOAD },
   { X86::CALL32r,             X86::CALL32m,             TB_FOLDED_LOAD },
   { X86::CALL32r_NT,          X86::CALL32m_NT,          TB_FOLDED_LOAD },
   { X86::CALL64r,             X86::CALL64m,             TB_FOLDED_LOAD },
   { X86::CALL64r_NT,          X86::CALL64m_NT,          TB_FOLDED_LOAD },
static const X86MemoryFoldTableEntry MemoryFoldTable0[] = {
   { X86::IMUL64r,             X86::IMUL64m,             TB_FOLDED_LOAD },
   { X86::IMUL8r,              X86::IMUL8m,              TB_FOLDED_LOAD },
   { X86::JMP16r,              X86::JMP16m,              TB_FOLDED_LOAD },
   { X86::JMP16r_NT,           X86::JMP16m_NT,           TB_FOLDED_LOAD },
   { X86::JMP32r,              X86::JMP32m,              TB_FOLDED_LOAD },
   { X86::JMP32r_NT,           X86::JMP32m_NT,           TB_FOLDED_LOAD },
   { X86::JMP64r,              X86::JMP64m,              TB_FOLDED_LOAD },
   { X86::JMP64r_NT,           X86::JMP64m_NT,           TB_FOLDED_LOAD },
-  { X86::MMX_MOVD64from64rr,  X86::MMX_MOVD64from64mr,  TB_FOLDED_STORE | TB_NO_REVERSE },
+  { X86::MMX_MOVD64from64rr,  X86::MMX_MOVQ64mr,        TB_FOLDED_STORE | TB_NO_REVERSE },
   { X86::MMX_MOVD64grr,       X86::MMX_MOVD64mr,        TB_FOLDED_STORE | TB_NO_REVERSE },
   { X86::MOV16ri,             X86::MOV16mi,             TB_FOLDED_STORE },
   { X86::MOV16rr,             X86::MOV16mr,             TB_FOLDED_STORE },
   { X86::MOV32ri,             X86::MOV32mi,             TB_FOLDED_STORE },
   { X86::MOV32rr,             X86::MOV32mr,             TB_FOLDED_STORE },
   { X86::MOV64ri32,           X86::MOV64mi32,           TB_FOLDED_STORE },
   { X86::MOV64rr,             X86::MOV64mr,             TB_FOLDED_STORE },
   { X86::MOV64toSDrr,         X86::MOV64mr,             TB_FOLDED_STORE | TB_NO_REVERSE },

llvm/test/CodeGen/X86/stack-folding-mmx.ll

 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    pushq %rbp
 ; CHECK-NEXT:    pushq %r15
 ; CHECK-NEXT:    pushq %r14
 ; CHECK-NEXT:    pushq %r13
 ; CHECK-NEXT:    pushq %r12
 ; CHECK-NEXT:    pushq %rbx
 ; CHECK-NEXT:    paddb %mm0, %mm0
-; CHECK-NEXT:    movq %mm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Folded Spill
+; CHECK-NEXT:    movq %mm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
 ; CHECK-NEXT:    #APP
 ; CHECK-NEXT:    nop
 ; CHECK-NEXT:    #NO_APP
 ; CHECK-NEXT:    movq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Reload
 ; CHECK-NEXT:    popq %rbx
 ; CHECK-NEXT:    popq %r12
 ; CHECK-NEXT:    popq %r13
 ; CHECK-NEXT:    popq %r14